NEURAL NETWORK SIGNAL PROCESSING FOR HANDWRITTEN CHARACTER RECOGNITION
Main Article Content
Abstract
A simulator software program that implements the neural network multi
layer perceptron trained by the Back propagation algorithm is presented. The
simulator is used to learn the ten numerals handwritten characters. A database
containing 1000 patterns written by 1000 different people is collected. The
percentage error of the training set is 1.3% and the percentage error of the test
set is 7.3%
Article Details
How to Cite
NEURAL NETWORK SIGNAL PROCESSING FOR HANDWRITTEN CHARACTER RECOGNITION. (2022). Journal of the College of Basic Education, 17(69), 133-138. https://doi.org/10.35950/cbej.vi.8259
Issue
Section
Articles for the humanities and pure sciences
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
NEURAL NETWORK SIGNAL PROCESSING FOR HANDWRITTEN CHARACTER RECOGNITION. (2022). Journal of the College of Basic Education, 17(69), 133-138. https://doi.org/10.35950/cbej.vi.8259